[
https://issues.apache.org/jira/browse/CASSANDRA-2178?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12995674#comment-12995674
]
Hudson commented on CASSANDRA-2178:
-----------------------------------
Integrated in Cassandra-0.7 #283 (See
[https://hudson.apache.org/hudson/job/Cassandra-0.7/283/])
Use a SynchronousQueue instead of LBQ so when memtable_flush_writers is >
1, it will allow actual parallel flushes.
patch by goffinet reviewed by jbellis for CASSANDRA-2178
> Memtable Flush writers doesn't actually flush in parallel
> ---------------------------------------------------------
>
> Key: CASSANDRA-2178
> URL: https://issues.apache.org/jira/browse/CASSANDRA-2178
> Project: Cassandra
> Issue Type: Bug
> Affects Versions: 0.7.2, 0.8
> Reporter: Chris Goffinet
> Assignee: Chris Goffinet
> Priority: Minor
> Fix For: 0.7.3, 0.8
>
> Attachments:
> 0001-Set-the-core-min-pool-size-to-memtable_flush_writers-v2.patch,
> 0001-Set-the-core-min-pool-size-to-memtable_flush_writers.patch
>
>
> The flushWriter JMXEnabledThreadPoolExecutor sets the core pool min to 1, and
> sets the LBQ to DatabaseDescriptor.getFlushWriters(). Increasing
> memtable_flush_writers should allow us to flush more in parallel. The pool
> will not grow until LBQ fills up to DatabaseDescriptor.getFlushWriters().
--
This message is automatically generated by JIRA.
-
For more information on JIRA, see: http://www.atlassian.com/software/jira
